mirror of
https://github.com/nlohmann/json.git
synced 2026-09-07 08:47:57 +00:00
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
81bc423ead |
@@ -1647,20 +1647,6 @@ class binary_writer
|
|||||||
return 'D'; // float 64
|
return 'D'; // float 64
|
||||||
}
|
}
|
||||||
|
|
||||||
/*!
|
|
||||||
@brief checks whether a JSON number fits into @a TargetType
|
|
||||||
@param[in] el a JSON number of either the signed or unsigned integer kind
|
|
||||||
@return whether @a el's value can be represented by @a TargetType without
|
|
||||||
wrapping, regardless of which of the two kinds it is stored as
|
|
||||||
*/
|
|
||||||
template<typename TargetType>
|
|
||||||
static bool bjdata_ndarray_value_in_range(const BasicJsonType& el)
|
|
||||||
{
|
|
||||||
return el.is_number_unsigned()
|
|
||||||
? value_in_range_of<TargetType>(el.template get<std::uint64_t>())
|
|
||||||
: value_in_range_of<TargetType>(el.template get<std::int64_t>());
|
|
||||||
}
|
|
||||||
|
|
||||||
/*!
|
/*!
|
||||||
@return false if the object is successfully converted to a bjdata ndarray, true if the type or size is invalid
|
@return false if the object is successfully converted to a bjdata ndarray, true if the type or size is invalid
|
||||||
*/
|
*/
|
||||||
@@ -1745,60 +1731,6 @@ class binary_writer
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// every element is cast to the (possibly narrower) C++ type matching
|
|
||||||
// dtype below; a value that does not fit that type would silently
|
|
||||||
// wrap (integers) or overflow to infinity (the "single" precision
|
|
||||||
// float) instead of being reported, so such an object falls back to
|
|
||||||
// a plain object encoding as well
|
|
||||||
for (const auto& el : value.at(key))
|
|
||||||
{
|
|
||||||
bool in_range = true;
|
|
||||||
switch (dtype)
|
|
||||||
{
|
|
||||||
case 'U':
|
|
||||||
case 'C':
|
|
||||||
case 'B':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::uint8_t>(el);
|
|
||||||
break;
|
|
||||||
case 'i':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::int8_t>(el);
|
|
||||||
break;
|
|
||||||
case 'u':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::uint16_t>(el);
|
|
||||||
break;
|
|
||||||
case 'I':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::int16_t>(el);
|
|
||||||
break;
|
|
||||||
case 'm':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::uint32_t>(el);
|
|
||||||
break;
|
|
||||||
case 'l':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::int32_t>(el);
|
|
||||||
break;
|
|
||||||
case 'M':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::uint64_t>(el);
|
|
||||||
break;
|
|
||||||
case 'L':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::int64_t>(el);
|
|
||||||
break;
|
|
||||||
case 'd':
|
|
||||||
{
|
|
||||||
const auto dval = el.template get<double>();
|
|
||||||
in_range = !std::isfinite(dval) ||
|
|
||||||
(dval >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
|
|
||||||
dval <= static_cast<double>((std::numeric_limits<float>::max)()));
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
default:
|
|
||||||
// 'D' (double) already spans the full range of number_float_t
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
if (!in_range)
|
|
||||||
{
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
oa->write_character('[');
|
oa->write_character('[');
|
||||||
oa->write_character('$');
|
oa->write_character('$');
|
||||||
oa->write_character(dtype);
|
oa->write_character(dtype);
|
||||||
|
|||||||
@@ -18655,20 +18655,6 @@ class binary_writer
|
|||||||
return 'D'; // float 64
|
return 'D'; // float 64
|
||||||
}
|
}
|
||||||
|
|
||||||
/*!
|
|
||||||
@brief checks whether a JSON number fits into @a TargetType
|
|
||||||
@param[in] el a JSON number of either the signed or unsigned integer kind
|
|
||||||
@return whether @a el's value can be represented by @a TargetType without
|
|
||||||
wrapping, regardless of which of the two kinds it is stored as
|
|
||||||
*/
|
|
||||||
template<typename TargetType>
|
|
||||||
static bool bjdata_ndarray_value_in_range(const BasicJsonType& el)
|
|
||||||
{
|
|
||||||
return el.is_number_unsigned()
|
|
||||||
? value_in_range_of<TargetType>(el.template get<std::uint64_t>())
|
|
||||||
: value_in_range_of<TargetType>(el.template get<std::int64_t>());
|
|
||||||
}
|
|
||||||
|
|
||||||
/*!
|
/*!
|
||||||
@return false if the object is successfully converted to a bjdata ndarray, true if the type or size is invalid
|
@return false if the object is successfully converted to a bjdata ndarray, true if the type or size is invalid
|
||||||
*/
|
*/
|
||||||
@@ -18753,60 +18739,6 @@ class binary_writer
|
|||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
// every element is cast to the (possibly narrower) C++ type matching
|
|
||||||
// dtype below; a value that does not fit that type would silently
|
|
||||||
// wrap (integers) or overflow to infinity (the "single" precision
|
|
||||||
// float) instead of being reported, so such an object falls back to
|
|
||||||
// a plain object encoding as well
|
|
||||||
for (const auto& el : value.at(key))
|
|
||||||
{
|
|
||||||
bool in_range = true;
|
|
||||||
switch (dtype)
|
|
||||||
{
|
|
||||||
case 'U':
|
|
||||||
case 'C':
|
|
||||||
case 'B':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::uint8_t>(el);
|
|
||||||
break;
|
|
||||||
case 'i':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::int8_t>(el);
|
|
||||||
break;
|
|
||||||
case 'u':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::uint16_t>(el);
|
|
||||||
break;
|
|
||||||
case 'I':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::int16_t>(el);
|
|
||||||
break;
|
|
||||||
case 'm':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::uint32_t>(el);
|
|
||||||
break;
|
|
||||||
case 'l':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::int32_t>(el);
|
|
||||||
break;
|
|
||||||
case 'M':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::uint64_t>(el);
|
|
||||||
break;
|
|
||||||
case 'L':
|
|
||||||
in_range = bjdata_ndarray_value_in_range<std::int64_t>(el);
|
|
||||||
break;
|
|
||||||
case 'd':
|
|
||||||
{
|
|
||||||
const auto dval = el.template get<double>();
|
|
||||||
in_range = !std::isfinite(dval) ||
|
|
||||||
(dval >= static_cast<double>(std::numeric_limits<float>::lowest()) &&
|
|
||||||
dval <= static_cast<double>((std::numeric_limits<float>::max)()));
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
default:
|
|
||||||
// 'D' (double) already spans the full range of number_float_t
|
|
||||||
break;
|
|
||||||
}
|
|
||||||
if (!in_range)
|
|
||||||
{
|
|
||||||
return true;
|
|
||||||
}
|
|
||||||
}
|
|
||||||
|
|
||||||
oa->write_character('[');
|
oa->write_character('[');
|
||||||
oa->write_character('$');
|
oa->write_character('$');
|
||||||
oa->write_character(dtype);
|
oa->write_character(dtype);
|
||||||
|
|||||||
@@ -214,4 +214,323 @@ static void BinaryToCbor(benchmark::State& state)
|
|||||||
}
|
}
|
||||||
BENCHMARK(BinaryToCbor)->RangeMultiplier(2)->Range(8, 8 << 12);
|
BENCHMARK(BinaryToCbor)->RangeMultiplier(2)->Range(8, 8 << 12);
|
||||||
|
|
||||||
|
//////////////////////////////////////////////////////////////////////////////
|
||||||
|
// parse binary formats
|
||||||
|
//////////////////////////////////////////////////////////////////////////////
|
||||||
|
|
||||||
|
// Only MessagePack had a read benchmark (FromMsgpack above, left untouched so
|
||||||
|
// its numbers stay comparable across releases). The benchmarks below cover the
|
||||||
|
// other formats, and read from a contiguous buffer as well as from a FILE*:
|
||||||
|
// most callers pass a container, and the two adapters compile to different
|
||||||
|
// code. The test data repository ships JSON only, so the input for each is
|
||||||
|
// derived at setup time by serializing a parsed test file.
|
||||||
|
|
||||||
|
/// binary format to benchmark; the _optimized variants add UBJSON/BJData size
|
||||||
|
/// and type annotations, which the readers handle in a separate code path
|
||||||
|
enum class binary_format
|
||||||
|
{
|
||||||
|
cbor,
|
||||||
|
msgpack,
|
||||||
|
ubjson,
|
||||||
|
ubjson_optimized,
|
||||||
|
bjdata,
|
||||||
|
bjdata_optimized,
|
||||||
|
bson
|
||||||
|
};
|
||||||
|
|
||||||
|
static std::vector<std::uint8_t> to_binary(const json& j, const binary_format format)
|
||||||
|
{
|
||||||
|
switch (format)
|
||||||
|
{
|
||||||
|
case binary_format::cbor:
|
||||||
|
return json::to_cbor(j);
|
||||||
|
case binary_format::msgpack:
|
||||||
|
return json::to_msgpack(j);
|
||||||
|
case binary_format::ubjson:
|
||||||
|
return json::to_ubjson(j);
|
||||||
|
case binary_format::ubjson_optimized:
|
||||||
|
return json::to_ubjson(j, true, true);
|
||||||
|
case binary_format::bjdata:
|
||||||
|
return json::to_bjdata(j);
|
||||||
|
case binary_format::bjdata_optimized:
|
||||||
|
return json::to_bjdata(j, true, true);
|
||||||
|
case binary_format::bson:
|
||||||
|
default:
|
||||||
|
return json::to_bson(j);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static json from_binary(const std::vector<std::uint8_t>& bytes, const binary_format format)
|
||||||
|
{
|
||||||
|
switch (format)
|
||||||
|
{
|
||||||
|
case binary_format::cbor:
|
||||||
|
return json::from_cbor(bytes);
|
||||||
|
case binary_format::msgpack:
|
||||||
|
return json::from_msgpack(bytes);
|
||||||
|
case binary_format::ubjson:
|
||||||
|
case binary_format::ubjson_optimized:
|
||||||
|
return json::from_ubjson(bytes);
|
||||||
|
case binary_format::bjdata:
|
||||||
|
case binary_format::bjdata_optimized:
|
||||||
|
return json::from_bjdata(bytes);
|
||||||
|
case binary_format::bson:
|
||||||
|
default:
|
||||||
|
return json::from_bson(bytes);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
static json from_binary(std::FILE* file, const binary_format format)
|
||||||
|
{
|
||||||
|
switch (format)
|
||||||
|
{
|
||||||
|
case binary_format::cbor:
|
||||||
|
return json::from_cbor(file);
|
||||||
|
case binary_format::msgpack:
|
||||||
|
return json::from_msgpack(file);
|
||||||
|
case binary_format::ubjson:
|
||||||
|
case binary_format::ubjson_optimized:
|
||||||
|
return json::from_ubjson(file);
|
||||||
|
case binary_format::bjdata:
|
||||||
|
case binary_format::bjdata_optimized:
|
||||||
|
return json::from_bjdata(file);
|
||||||
|
case binary_format::bson:
|
||||||
|
default:
|
||||||
|
return json::from_bson(file);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
/*!
|
||||||
|
@brief serialize a parsed test file to @a format
|
||||||
|
|
||||||
|
Returns an empty vector and marks the benchmark as skipped if the file cannot
|
||||||
|
be represented in the format, rather than letting the exception escape: BSON
|
||||||
|
requires an object at the top level, and several test files are arrays.
|
||||||
|
*/
|
||||||
|
static std::vector<std::uint8_t> binary_input(benchmark::State& state, const char* filename, const binary_format format)
|
||||||
|
{
|
||||||
|
std::ifstream f(filename);
|
||||||
|
std::string const str((std::istreambuf_iterator<char>(f)), std::istreambuf_iterator<char>());
|
||||||
|
const json j = json::parse(str);
|
||||||
|
|
||||||
|
if (format == binary_format::bson && !j.is_object())
|
||||||
|
{
|
||||||
|
state.SkipWithError("BSON requires an object at the top level");
|
||||||
|
return {};
|
||||||
|
}
|
||||||
|
|
||||||
|
return to_binary(j, format);
|
||||||
|
}
|
||||||
|
|
||||||
|
static void FromBinaryBuffer(benchmark::State& state, const char* filename, const binary_format format)
|
||||||
|
{
|
||||||
|
const std::vector<std::uint8_t> bytes = binary_input(state, filename, format);
|
||||||
|
if (bytes.empty())
|
||||||
|
{
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
for (auto _ : state)
|
||||||
|
{
|
||||||
|
// the value is destroyed outside the timed section, because destroying
|
||||||
|
// a large DOM is not what this benchmark measures
|
||||||
|
state.PauseTiming();
|
||||||
|
auto* j = new json();
|
||||||
|
state.ResumeTiming();
|
||||||
|
|
||||||
|
*j = from_binary(bytes, format);
|
||||||
|
|
||||||
|
state.PauseTiming();
|
||||||
|
delete j;
|
||||||
|
state.ResumeTiming();
|
||||||
|
}
|
||||||
|
|
||||||
|
state.SetBytesProcessed(state.iterations() * bytes.size());
|
||||||
|
}
|
||||||
|
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / floats, TEST_DATA_DIRECTORY "/regression/floats.json", binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, cbor / signed_ints, TEST_DATA_DIRECTORY "/regression/signed_ints.json", binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::msgpack);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::msgpack);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::msgpack);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, msgpack / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::msgpack);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / jeopardy, TEST_DATA_DIRECTORY "/jeopardy/jeopardy.json", binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson_optimized / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson_optimized);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, ubjson_optimized / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson_optimized);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bjdata);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata_optimized / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bjdata_optimized);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, bjdata_optimized / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata_optimized);
|
||||||
|
// BSON requires an object at the top level, so the array-rooted test files
|
||||||
|
// (jeopardy and the regression files) cannot be captured here
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, bson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::bson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, bson / citm_catalog, TEST_DATA_DIRECTORY "/nativejson-benchmark/citm_catalog.json", binary_format::bson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryBuffer, bson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bson);
|
||||||
|
|
||||||
|
static void FromBinaryFile(benchmark::State& state, const char* filename, const binary_format format)
|
||||||
|
{
|
||||||
|
const std::vector<std::uint8_t> bytes = binary_input(state, filename, format);
|
||||||
|
if (bytes.empty())
|
||||||
|
{
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
const char* tmp = "benchmark_input.bin";
|
||||||
|
std::ofstream o(tmp, std::ios::binary);
|
||||||
|
o.write(reinterpret_cast<const char*>(bytes.data()), static_cast<std::streamsize>(bytes.size()));
|
||||||
|
o.flush();
|
||||||
|
o.close();
|
||||||
|
|
||||||
|
for (auto _ : state)
|
||||||
|
{
|
||||||
|
state.PauseTiming();
|
||||||
|
auto* j = new json();
|
||||||
|
auto* file = std::fopen(tmp, "rb");
|
||||||
|
state.ResumeTiming();
|
||||||
|
|
||||||
|
*j = from_binary(file, format);
|
||||||
|
|
||||||
|
state.PauseTiming();
|
||||||
|
std::fclose(file);
|
||||||
|
delete j;
|
||||||
|
state.ResumeTiming();
|
||||||
|
}
|
||||||
|
|
||||||
|
state.SetBytesProcessed(state.iterations() * bytes.size());
|
||||||
|
}
|
||||||
|
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryFile, cbor / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryFile, cbor / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryFile, ubjson / canada, TEST_DATA_DIRECTORY "/nativejson-benchmark/canada.json", binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryFile, ubjson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryFile, bjdata / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bjdata);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryFile, bson / twitter, TEST_DATA_DIRECTORY "/nativejson-benchmark/twitter.json", binary_format::bson);
|
||||||
|
|
||||||
|
//////////////////////////////////////////////////////////////////////////////
|
||||||
|
// parse binary formats: value shapes
|
||||||
|
//////////////////////////////////////////////////////////////////////////////
|
||||||
|
|
||||||
|
// The test files above are wide and shallow, but the readers' cost is per
|
||||||
|
// container, so these cover the shapes that stress the container handling
|
||||||
|
// itself. Every shape is wrapped in an object so that BSON, which requires an
|
||||||
|
// object at the top level, measures the same value as the other formats.
|
||||||
|
|
||||||
|
/// deeply nested arrays: one container per level, no other work
|
||||||
|
static json make_nested()
|
||||||
|
{
|
||||||
|
json nested = json::array();
|
||||||
|
json* p = &nested;
|
||||||
|
for (std::size_t i = 1; i < 1000; ++i)
|
||||||
|
{
|
||||||
|
p->push_back(json::array());
|
||||||
|
p = &p->operator[](0);
|
||||||
|
}
|
||||||
|
|
||||||
|
json j = json::object();
|
||||||
|
j["data"] = std::move(nested);
|
||||||
|
return j;
|
||||||
|
}
|
||||||
|
|
||||||
|
/// many sibling containers: maximum container churn, minimum nesting
|
||||||
|
static json make_containers()
|
||||||
|
{
|
||||||
|
json data = json::array();
|
||||||
|
for (std::size_t i = 0; i < 100000; ++i)
|
||||||
|
{
|
||||||
|
data.push_back(json::array({1, 2}));
|
||||||
|
}
|
||||||
|
|
||||||
|
json j = json::object();
|
||||||
|
j["data"] = std::move(data);
|
||||||
|
return j;
|
||||||
|
}
|
||||||
|
|
||||||
|
/// one flat array of numbers: the scalar decoding path, which must not move
|
||||||
|
static json make_scalars()
|
||||||
|
{
|
||||||
|
json data = json::array();
|
||||||
|
for (std::size_t i = 0; i < 1000000; ++i)
|
||||||
|
{
|
||||||
|
data.push_back(i);
|
||||||
|
}
|
||||||
|
|
||||||
|
json j = json::object();
|
||||||
|
j["data"] = std::move(data);
|
||||||
|
return j;
|
||||||
|
}
|
||||||
|
|
||||||
|
static void FromBinaryShape(benchmark::State& state, json (*build)(), const binary_format format)
|
||||||
|
{
|
||||||
|
const std::vector<std::uint8_t> bytes = to_binary(build(), format);
|
||||||
|
|
||||||
|
for (auto _ : state)
|
||||||
|
{
|
||||||
|
state.PauseTiming();
|
||||||
|
auto* j = new json();
|
||||||
|
state.ResumeTiming();
|
||||||
|
|
||||||
|
*j = from_binary(bytes, format);
|
||||||
|
|
||||||
|
state.PauseTiming();
|
||||||
|
delete j;
|
||||||
|
state.ResumeTiming();
|
||||||
|
}
|
||||||
|
|
||||||
|
state.SetBytesProcessed(state.iterations() * bytes.size());
|
||||||
|
}
|
||||||
|
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, nested / cbor, make_nested, binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, nested / msgpack, make_nested, binary_format::msgpack);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, nested / ubjson, make_nested, binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, nested / bjdata, make_nested, binary_format::bjdata);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, nested / bson, make_nested, binary_format::bson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, containers / cbor, make_containers, binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, containers / msgpack, make_containers, binary_format::msgpack);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson, make_containers, binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, containers / ubjson_optimized, make_containers, binary_format::ubjson_optimized);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, containers / bjdata, make_containers, binary_format::bjdata);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, containers / bson, make_containers, binary_format::bson);
|
||||||
|
// BSON names every array element, so a large array measures key generation
|
||||||
|
// rather than scalar decoding and is left out here
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, scalars / cbor, make_scalars, binary_format::cbor);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, scalars / msgpack, make_scalars, binary_format::msgpack);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, scalars / ubjson, make_scalars, binary_format::ubjson);
|
||||||
|
BENCHMARK_CAPTURE(FromBinaryShape, scalars / bjdata, make_scalars, binary_format::bjdata);
|
||||||
|
|
||||||
|
/*!
|
||||||
|
@brief parse an indefinite-length CBOR string
|
||||||
|
|
||||||
|
The writer never emits this form, so the input is assembled by hand: 0x7F
|
||||||
|
opens the string, each chunk is a one-character string, and 0xFF closes it.
|
||||||
|
*/
|
||||||
|
static void FromCborChunkedString(benchmark::State& state, const std::size_t chunks)
|
||||||
|
{
|
||||||
|
std::vector<std::uint8_t> bytes;
|
||||||
|
bytes.reserve(2 * chunks + 2);
|
||||||
|
bytes.push_back(0x7F);
|
||||||
|
for (std::size_t i = 0; i < chunks; ++i)
|
||||||
|
{
|
||||||
|
bytes.push_back(0x61); // string of length 1
|
||||||
|
bytes.push_back(0x61); // 'a'
|
||||||
|
}
|
||||||
|
bytes.push_back(0xFF);
|
||||||
|
|
||||||
|
for (auto _ : state)
|
||||||
|
{
|
||||||
|
json j = json::from_cbor(bytes);
|
||||||
|
benchmark::DoNotOptimize(j);
|
||||||
|
}
|
||||||
|
|
||||||
|
state.SetBytesProcessed(state.iterations() * bytes.size());
|
||||||
|
}
|
||||||
|
|
||||||
|
BENCHMARK_CAPTURE(FromCborChunkedString, 10000 chunks, 10000);
|
||||||
|
|
||||||
BENCHMARK_MAIN();
|
BENCHMARK_MAIN();
|
||||||
|
|||||||
@@ -2776,53 +2776,6 @@ TEST_CASE("BJData")
|
|||||||
CHECK(out_num.at(0) == '{');
|
CHECK(out_num.at(0) == '{');
|
||||||
CHECK(json::from_bjdata(out_num) == j_num);
|
CHECK(json::from_bjdata(out_num) == j_num);
|
||||||
}
|
}
|
||||||
|
|
||||||
SECTION("ndarray with out-of-range _ArrayData_ elements stays as object")
|
|
||||||
{
|
|
||||||
// each element is cast to the (possibly narrower) C++ type
|
|
||||||
// named by _ArrayType_ before being written; a value that
|
|
||||||
// does not fit that type would silently wrap instead of
|
|
||||||
// being reported, so such an object falls back to a plain
|
|
||||||
// object encoding that still round-trips (see GitHub issue #5403)
|
|
||||||
|
|
||||||
// an unsigned element that does not fit uint8
|
|
||||||
json const j_uint8 = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2}}, {"_ArrayData_", {1, 256}}});
|
|
||||||
const auto out_uint8 = json::to_bjdata(j_uint8);
|
|
||||||
CHECK(out_uint8.at(0) == '{');
|
|
||||||
CHECK(json::from_bjdata(out_uint8) == j_uint8);
|
|
||||||
|
|
||||||
// a signed element that does not fit int8
|
|
||||||
json const j_int8 = json({{"_ArrayType_", "int8"}, {"_ArraySize_", {2}}, {"_ArrayData_", {1, 200}}});
|
|
||||||
const auto out_int8 = json::to_bjdata(j_int8);
|
|
||||||
CHECK(out_int8.at(0) == '{');
|
|
||||||
CHECK(json::from_bjdata(out_int8) == j_int8);
|
|
||||||
|
|
||||||
// a negative element is likewise out of range for an
|
|
||||||
// unsigned _ArrayType_
|
|
||||||
json const j_uint16_neg = json({{"_ArrayType_", "uint16"}, {"_ArraySize_", {2}}, {"_ArrayData_", {1, -1}}});
|
|
||||||
const auto out_uint16_neg = json::to_bjdata(j_uint16_neg);
|
|
||||||
CHECK(out_uint16_neg.at(0) == '{');
|
|
||||||
CHECK(json::from_bjdata(out_uint16_neg) == j_uint16_neg);
|
|
||||||
|
|
||||||
// a double element that overflows to infinity when narrowed
|
|
||||||
// to the "single" (float) precision named by _ArrayType_
|
|
||||||
json const j_single = json({{"_ArrayType_", "single"}, {"_ArraySize_", {2}}, {"_ArrayData_", {1.5, 1e40}}});
|
|
||||||
const auto out_single = json::to_bjdata(j_single);
|
|
||||||
CHECK(out_single.at(0) == '{');
|
|
||||||
CHECK(json::from_bjdata(out_single) == j_single);
|
|
||||||
|
|
||||||
// in-range boundary values still use the compact ndarray encoding
|
|
||||||
json const j_uint8_ok = json({{"_ArrayType_", "uint8"}, {"_ArraySize_", {2}}, {"_ArrayData_", {0, 255}}});
|
|
||||||
CHECK(json::to_bjdata(j_uint8_ok) == std::vector<uint8_t>({'[', '$', 'U', '#', '[', 'i', 2, ']', 0, 255}));
|
|
||||||
|
|
||||||
json const j_int8_ok = json({{"_ArrayType_", "int8"}, {"_ArraySize_", {2}}, {"_ArrayData_", {-128, 127}}});
|
|
||||||
CHECK(json::to_bjdata(j_int8_ok) == std::vector<uint8_t>({'[', '$', 'i', '#', '[', 'i', 2, ']', 0x80, 0x7F}));
|
|
||||||
|
|
||||||
json const j_single_ok = json({{"_ArrayType_", "single"}, {"_ArraySize_", {1}}, {"_ArrayData_", {1.5}}});
|
|
||||||
const auto out_single_ok = json::to_bjdata(j_single_ok);
|
|
||||||
CHECK(out_single_ok.at(0) == '[');
|
|
||||||
CHECK(json::from_bjdata(out_single_ok) == json({1.5f}));
|
|
||||||
}
|
|
||||||
}
|
}
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|||||||
Reference in New Issue
Block a user